tilelang.cpu.toolchain
======================

.. py:module:: tilelang.cpu.toolchain

.. autoapi-nested-parse::

   OpenMP compile-flag helpers for CPU kernels (``tl.cpu_parallel``).

   The kernel shared library must link the *same* libomp copy the host process
   already loaded, otherwise macOS dyld raises ``OMP: Error #15`` (multiple
   OpenMP runtimes). Detection order (mirrors torch inductor's cpp_builder):

   1. ``OMP_PREFIX`` environment variable (a prefix with ``include/`` and
      ``lib/``);
   2. an already-imported (or importable) torch's bundled ``libomp.dylib``;
   3. the conda prefix of the current interpreter;
   4. Homebrew's ``libomp``.

   On Linux the compiler runtime ``-fopenmp`` is used directly. When no runtime
   can be found the OpenMP flags are dropped with a warning: unknown pragmas
   are ignored by the compiler, so the kernel stays correct, just serial.



Functions
---------

.. autoapisummary::

   tilelang.cpu.toolchain.get_compile_flags
   tilelang.cpu.toolchain.get_openmp_compile_flags


Module Contents
---------------

.. py:function:: get_compile_flags(target, pass_configs, *, execution_backend)

   CPU flags for the selected target, pass configuration, and adapter.

   LLVM uses TVM's thread pool, so OpenMP flags only apply to the C target.
   Disabled parallelization leaves the serial compile command unchanged.


.. py:function:: get_openmp_compile_flags()

   Compile flags for OpenMP CPU kernels: ``-O2`` plus OpenMP flags.